OmniHuman-1

Closed weights ByteDance February 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
ByteDance
Organisation type
Industry
Country
China
Published
13 February 2025
Authors
Gaojie Lin, Jianwen Jiang, Jiaqi Yang, Zerong Zheng, Chao Liang

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Video, Vision, Audio
Task
Video generation, Image-to-video

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Last updated
28 November 2025

What the numbers mean

Where it came from

OmniHuman-1 was published by ByteDance, in China, in February 2025. industry is the category the publisher falls under.

It works in Video, Vision, Audio, and is recorded as doing video generation, Image-to-video.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Answers

OmniHuman-1 — common questions

01

When was OmniHuman-1 released?

OmniHuman-1 was published in February 2025.

02

What is OmniHuman-1 used for?

OmniHuman-1 works in Video, Vision, Audio, and is recorded as handling video generation, Image-to-video. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

03

What GPU do I need to run OmniHuman-1?

None. OmniHuman-1 is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

04

Is OmniHuman-1 open source?

No. OmniHuman-1 has not had its weights published, so it exists only as a service controlled by its owner.

05

How many parameters does OmniHuman-1 have?

No parameter count has been published for OmniHuman-1, which is why no memory or speed figure appears on this page.

06

Who created OmniHuman-1?

OmniHuman-1 was published by ByteDance, based in China, categorised as industry.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.